# TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning

Source: [arXiv](https://arxiv.org/abs/2607.05380v1)  
Feed7 permalink: https://feed7.dev/p/2607-05380v1-1a0sfhm  
Published: Unknown  
Trust: Needs Review (needs_review)

## Why Included

TabPack trains many MLPs with sampled hyperparameters in one run and picks ensemble members on the fly, matching tuned tabular baselines out of the box — a default MacBook run beat some baselines' GPU tuning time.

## Source Summary

**The gist** **TabPack** is an MLP ensemble for tabular deep learning that, in a **single run**, samples and trains many MLPs with different hyperparameters in parallel and selects ensemble members on the fly during training. You supply hyperparameter **ranges** instead of exact values; on medium-to-large public datasets, defaults match extensively tuned prior methods.

## Practical Implication

**Why it matters** Off the agent path, but handy if your product carries a tabular ML component: it removes the tuning loop that dominates tabular deep-learning cost. The authors report the **default configuration on a modern MacBook** finished in less time than tuning some baselines took on an **industry-grade GPU** — cheap enough to fold into a local pipeline.

## Agent-Ready Context

**The gist** **TabPack** is an MLP ensemble for tabular deep learning that, in a **single run**, samples and trains many MLPs with different hyperparameters in parallel and selects ensemble members on the fly during training. You supply hyperparameter **ranges** instead of exact values; on medium-to-large public datasets, defaults match extensively tuned prior methods.

**Why it matters** Off the agent path, but handy if your product carries a tabular ML component: it removes the tuning loop that dominates tabular deep-learning cost. The authors report the **default configuration on a modern MacBook** finished in less time than tuning some baselines took on an **industry-grade GPU** — cheap enough to fold into a local pipeline.

**Watch out** The comparison set is **tuned prior deep-learning methods**; the abstract doesn't say how TabPack fares against **gradient-boosted trees**, still the default tabular baseline, or in cases that genuinely need specialized hyperparameters.

## Context Map

- Layer: model
- Domains: data
- Topics: None

## Uncertainty

- The comparison set is **tuned prior deep-learning methods**; the abstract doesn't say how TabPack fares against **gradient-boosted trees**, still the default tabular baseline, or in cases that genuinely need specialized hyperparameters.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.